3 problems

Information-bottleneck explanation. The underlying reason why training regularization has inferior downstream performance is that though it lowers the value of $I(Z_1;Z_2)$, it fai…

Let $A$ denote an image transformation, $C$ denote class information, and $X$ denote the transformed image. A transformation is global when it changes pixel positions, whereas it i…

Let multi-sample versions of the mutual-information estimators $\operatorname{NWJ}$, $\operatorname{TUBA}$ and $\operatorname{FLO}$ be used in empirical applications such as self-s…